© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 12688
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "un" and other similar repeated words in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mn rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     climático
    -0.50
     navideño
    -0.47
     tenisky
    -0.46
     extérieure
    -0.46
    extré
    -0.46
     tué
    -0.45
     wensen
    -0.45
     própri
    -0.45
     tyto
    -0.45
     zijne
    -0.44
    POSITIVE LOGITS
    mn
    0.96
     mn
    0.55
    cmath
    0.52
    endcsname
    0.50
    ectoria
    0.49
    mfenced
    0.48
     HN
    0.47
    bcryptjs
    0.47
    $
    
    0.47
    msup
    0.47
    Activations Density 0.002%

    No Known Activations